Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    installment or payment-related terms in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to installments or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.66
    çĦ
    -0.62
     wid
    -0.61
     unim
    -0.61
    clinton
    -0.60
     Rampage
    -0.58
     straw
    -0.57
     Tablet
    -0.56
    enegger
    -0.54
     boarding
    -0.54
    POSITIVE LOGITS
    ciating
    1.29
    ution
    0.89
    olated
    0.85
    utions
    0.84
    rative
    0.84
    lished
    0.83
    lishes
    0.82
    utes
    0.82
    iliar
    0.82
    cled
    0.80
    Act Density 0.121%

    No Known Activations